Robotic script generation based on process variation detection

Abstract

Techniques for generating Robotic Scripts via Process Variation Detection are described. In one example, captured process steps related to an activity performed in an application may be received. Variations of the process steps are then determined by training a first Artificial Neural Network (ANN) with the captured process steps. A set of the process steps for performing the activity, may then be determined based on the determined variations of the process steps. Robotic scripts may be generated using the determined set of process steps to perform the activity.

What is claimed is: 
     
         1 . A system comprising:
 a processor; and   a memory communicatively coupled to the processor, wherein the memory is capable of executing a plurality of modules stored in the memory, and wherein the plurality of modules comprises:
 a receiving module to receive captured process steps related to an activity performed while interacting with an application; 
 a processing module to determine variations of process steps in performing the activity by training a first Artificial Neural Network (ANN) using the captured process steps; 
 an optimization module to determine a set of the process steps for performing the activity based on the determined variations of the process steps; and 
 a script generation module to generate a robotic script to perform the activity using the determined set of process steps. 
   
     
     
         2 . The system of  claim 1 , wherein the script generation module generates the robotic script automatically. 
     
     
         3 . The system of  claim 1 , wherein the script generation module generates the robotic script manually in a simulated environment. 
     
     
         4 . The system of  claim 1 , wherein the captured process steps correspond to a sequence of User-Interface (UI) interactions carried out for performing the activity. 
     
     
         5 . The system of  claim 1 , wherein the captured process steps are fed to the first ANN in the form of Extensible Markup Language (XML) files and/or hash codes. 
     
     
         6 . The system of  claim 1 , wherein the first ANN is a Recurrent Neural Network (RNN), wherein the RNN is a Long Short-Term Memory (LSTM) network. 
     
     
         7 . The system of  claim 1 , wherein the robotic script generation module is configured to:
 receive an input document by the receiving module;   classify the input document using a second ANN by a classification module;   determine the input document corresponds to the activity based on the classification by the processing module; and   automatically fill a form related to the input document by executing the set of process steps upon determining that the input document corresponds to the activity by the robotic script generation module.   
     
     
         8 . The system of  claim 7 , wherein the input document is a text document and/or an image document. 
     
     
         9 . The system of  claim 7 , wherein the second ANN is a Feed Forward Neural Network, wherein the Feed Forward Neural Network is a Convolutional Neural Network (CNN) or a Deep Auto Encoder. 
     
     
         10 . The system of  claim 9 , wherein the classification module is configured to:
 classify the text document using the Deep Auto Encoder; and   classify the image document using the CNN.   
     
     
         11 . A computer-implemented method comprising:
 receiving captured process steps related to an activity performed while interacting with an application;   determining variations of process steps in performing the activity by training a first Artificial Neural Network (ANN) using the captured process steps;   determining a set of the process steps for performing the activity based on the determined variations of the process steps; and   generating a robotic script to perform the activity using the determined set of process steps.   
     
     
         12 . The computer-implemented method of  claim 11 , wherein the robotic script is generated automatically, or manually in a simulated environment. 
     
     
         13 . The computer-implemented method of  claim 11 , wherein the captured process steps correspond to a sequence of User-Interface (UI) interactions carried out for performing the activity. 
     
     
         14 . The computer-implemented method of  claim 11 , wherein the captured process steps are fed to the first ANN in the form of Extensible Markup Language (XML) files and/or hash codes. 
     
     
         15 . The computer-implemented method of  claim 11 , wherein the first ANN is a Recurrent Neural Network (RNN), wherein the RNN is a Long Short-Term Memory (LSTM) network. 
     
     
         16 . The computer-implemented method of  claim 11 , wherein generating the robotic script to perform the activity comprises:
 receiving an input document;   classifying the input document using a second ANN;   determining the input document corresponds to the activity based on the classification; and   automatically filling a form related to the input document by executing the set of process steps upon determining that the input document corresponds to the activity.   
     
     
         17 . The computer-implemented method of  claim 16 , wherein the second ANN is a Feed Forward Neural Network, wherein the Feed Forward Neural Network is a Convolutional Neural Network (CNN) or a Deep Auto Encoder. 
     
     
         18 . The computer-implemented method of  claim 17 , wherein classifying the input document comprises:
 classifying the input document using the Deep Auto Encoder upon determining that the input document is a text document; and   classifying the input document using the CNN upon determining that the input document is an image document.   
     
     
         19 . A non-transitory machine-readable medium storing instructions executable by a processing resource to:
 receive captured process steps related to an activity performed while interacting with an application;   determine variations of process steps in performing the activity by training a first Artificial Neural Network (ANN) using the captured process steps;   determine a set of the process steps for performing the activity based on the determined variations of the process steps; and   generate a robotic script to perform the activity using the determined set of process steps.   
     
     
         20 . The non-transitory machine-readable medium of  claim 19 , wherein the robotic script is generated automatically, or manually in a simulated environment. 
     
     
         21 . The non-transitory machine-readable medium of  claim 19 , wherein the first ANN is a Long Short-Term Memory (LSTM) Network. 
     
     
         22 . The non-transitory machine-readable medium of  claim 19 , wherein generating the robotic script to perform the activity comprises instructions to:
 receive an input document;   classify the input documents using a second ANN;   determining the input document corresponds to the activity based on the classification; and   automatically fill a form related to the input document by executing the set of process steps upon determining that the input document corresponds to the activity.   
     
     
         23 . The non-transitory machine-readable medium of  claim 22 , wherein the second ANN is a Convolutional Neural Network (CNN) or a Deep Auto Encoder.